Mentored Research ProjectsRepresentative program

AI-Driven Defect Prediction and Process Control in Metal Additive Manufacturing

Explore data-driven approaches to manufacturing defects, prediction, and process-quality questions.

Overview

This project investigates relationships between process information, defects, and quality in metal additive manufacturing. Learners work with approved data or simulations to define a prediction task, evaluate a model, and discuss process implications. Access to manufacturing equipment is not implied by the online program description.

Learning goals and possible work

Proposed learning outcomes for this program example:

  • Define a meaningful defect-prediction question and target variable.
  • Develop and validate a baseline or machine-learning model.
  • Explain process implications, data limits, and further validation needs.

Illustrative project milestones

The sequence below illustrates how this program’s content can be organized. Topics, pacing, and project depth are adapted for each offering. This is not an archived record of a specific cohort’s weekly syllabus.

  1. 01Manufacturing context and a bounded research problem
  2. 02Defect mechanisms and relevant process variables
  3. 03Data access, labeling, and quality checks
  4. 04Feature construction and baseline prediction
  5. 05Training and evaluating a predictive model
  6. 06Interpreting model behavior and process implications
  7. 07Sensitivity checks and process-control concepts
  8. 08Technical report and research presentation
Ask About This Program Back to the Program Portfolio

Related program examples